Why is plausibility surprisingly problematic as an XAI criterion?
This addresses the problem of flawed evaluation metrics in XAI for researchers and practitioners, highlighting incremental insights into existing methodological critiques.
The paper critically examines plausibility as a criterion in explainable AI (XAI), arguing that it is invalid for measuring explainability and leads to unethical issues like misleading explanations and reduced user trust, advocating for its discontinuation.
Explainable artificial intelligence (XAI) is motivated by the problem of making AI predictions understandable, transparent, and responsible, as AI becomes increasingly impactful in society and high-stakes domains. The evaluation and optimization criteria of XAI are gatekeepers for XAI algorithms to achieve their expected goals and should withstand rigorous inspection. To improve the scientific rigor of XAI, we conduct a critical examination of a common XAI criterion: plausibility. Plausibility assesses how convincing the AI explanation is to humans, and is usually quantified by metrics of feature localization or feature correlation. Our examination shows that plausibility is invalid to measure explainability, and human explanations are not the ground truth for XAI, because doing so ignores the necessary assumptions underpinning an explanation. Our examination further reveals the consequences of using plausibility as an XAI criterion, including increasing misleading explanations that manipulate users, deteriorating users' trust in the AI system, undermining human autonomy, being unable to achieve complementary human-AI task performance, and abandoning other possible approaches of enhancing understandability. Due to the invalidity of measurements and the unethical issues, this position paper argues that the community should stop using plausibility as a criterion for the evaluation and optimization of XAI algorithms. We also delineate new research approaches to improve XAI in trustworthiness, understandability, and utility to users, including complementary human-AI task performance.